de Meta líder abierto multimodal modelo fundacional pairing 128K contexto windows con cross-attention visual encoders un interpret complejo charts, graphs, y imágenes.
Technical Specifications
- Provider
- Meta
- Category
- flagship
- Release Date
- 2024-09
- Batch API Discount
- Standard rate
- Consumer Subscription
- Free / Self-Hosted
- Reasoning Effort Control
- Fixed
- Structured Outputs
- Yes
- Output Modalities
- text
- Official Documentation
- Visit Official Docs ↗
Data Privacy, Licensing & Deployment Governance
Official Provider Release Intelligence, API Quotas & Agentic Specs
- Official API Model ID (SDK String)
- meta-llama/Llama-3.2-90B-Vision
- Supported SDK & API Protocol
- OpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI
- Lifecycle & Deprecation Status
- Legacy Stable (Upgrade path available in Meta lineup)
- Production Rate Limits (RPM & TPM)
- Unlimited (Hardware-bound on self-hosted GPU) / 10,000 RPM Cloud · Unlimited local throughput / 10M+ TPM Managed Cloud
- Long-Context Pricing Tier (>128K / >200K)
- Free across full context window (only KV-cache VRAM scales)
- Prompt Cache Write & TTL Policy
- Automatic prefix KV-caching in vLLM / SGLang (0 cost)
- Computer Use & Browser GUI Agent
- API / CLI Tool-Use & DOM Agent ready (no raw pixel desktop click loop)
- MCP & Parallel Tool Calling
- Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema
- Web Search Grounding & Code Sandbox
- Supported via external Tavily/Exa Search & E2B/Docker Sandbox tools
- Fine-Tuning & Distillation Support
- Full Weights SFT, LoRA, QLoRA, DPO & GRPO RL (Unsloth / Axolotl / Llama-Factory)
- Multimodal Tokenization Billing
- Text BPE (~4 chars/token) · Vision (~258–765 tokens per image tile)
- Weights Precision & Quantization
- BF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0)
- Minimum GPU VRAM Requirement
- 56 GB VRAM (4-bit Quantized) · 194 GB VRAM (Native BF16)
- Supported Inference Engines
- vLLM, SGLang, Ollama, llama.cpp, TensorRT-LLM, HuggingFace TGI
- System Card & Safety Framework
- Open-Weights System Card + Customizable Guardrail Layer (Llama Guard / ShieldGemma)
- Enterprise Compliance (SOC2 / HIPAA / ZDR)
- 100% Air-Gapped On-Premises / Private VPC · Full HIPAA, GDPR & SOC2 Control
Llama 3.2 90B Vision Cost, Context, Hardware & API Integration
Open-weights or free-tier model: $0 API license cost when self-hosted.
Same Monthly Workload Cost Across Popular Reference Models
Live Prompt Paste Tokenizer & Cost Counter
Paste real system instructions, JSON schemas, or code to measure BPE token counts across tokenizers.
Hybrid Prompt Routing Cascade Simulator
Route routine queries to a fast lightweight model ($0.15/1M) and escalate only complex reasoning turns to Llama 3.2 90B Vision:
Benchmark Scores & 6-Axis Capability Radar
- SWE-bench Verified
- 28.5%
- GPQA Diamond
- 48.2%
- MMLU-Pro
- 73.5%
- HumanEval
- 84.8%
- Chatbot Arena Elo
- 1260pts
Strengths
- nativo abierto visual razonamiento un través de complejo documentos, schematics, y maps
- Cross-attention adapter arquitectura preserves texto razonamiento mientras que unlocking visión
- 128,000 token ventana de contexto
Limitations & Trade-offs
- requiere especializado multi-GPU servers para alto-rendimiento visual batching
- salida generación capped un 8,192 tokens
Editorial Assessment
el modelo que unlocked alto-precisión visual razonamiento para autohospedado empresarial infraestructura.
Best for: autohospedado OCR extracción, visual documento análisis, y privado empresarial multimodal agentes
Compare Llama 3.2 90B Vision
Frequently Asked Questions about Llama 3.2 90B Vision
How much does the Llama 3.2 90B Vision API cost per 1M tokens?+
Llama 3.2 90B Vision by Meta is priced at $0 per 1M input tokens and $0 per 1M output tokens. With prompt caching enabled, cached input tokens cost $0 per 1M tokens, and asynchronous Batch API requests receive a 0% discount.
Should I use a $20/month subscription or the Llama 3.2 90B Vision pay-as-you-go API?+
A flat $20/month consumer subscription is predictable for daily interactive chat and manual coding. However, if you are building software, running automated workflows, or sending low-to-moderate volume with prompt caching enabled, the pay-as-you-go API is typically far more cost-effective and offers higher rate limits without manual UI caps.
How many words and pages fit in Llama 3.2 90B Vision's context window?+
Llama 3.2 90B Vision features a 128K tokens context window, which equals approximately 96,000 English words or ~256 standard single-spaced pages in a single prompt. Its maximum output generation per turn is 8,192 tokens.
Can I run Llama 3.2 90B Vision locally on my own GPU (Open Weights)?+
Yes, Llama 3.2 90B Vision (90B) releases open weights that can be self-hosted locally or on private cloud GPUs using vLLM, Ollama, SGLang, or llama.cpp.
Does Meta train on data sent to the Llama 3.2 90B Vision API, and is commercial use allowed?+
100% Isolated when self-hosted on private GPUs or VPC. License tier: Llama Community License (Commercial Permitted). Full commercial ownership of generated outputs. Supported deployment channels include: Self-Hosted GPU (vLLM / Ollama), Private VPC, or Managed Serverless API.
How does Llama 3.2 90B Vision perform on coding and reasoning benchmarks?+
Llama 3.2 90B Vision achieves a composite Intelligence Index of 44/100, scoring 28.5% on SWE-bench Verified, 48.2% on GPQA Diamond, 73.5% on MMLU-Pro, and 1260 pts on Chatbot Arena Elo.
What is Llama 3.2 90B Vision best used for?+
Llama 3.2 90B Vision is best suited for: autohospedado OCR extracción, visual documento análisis, y privado empresarial multimodal agentes. Assessment: el modelo que unlocked alto-precisión visual razonamiento para autohospedado empresarial infraestructura.
Meta Family Lineage, Routing Tiers & Upgrade Path
Step down to a lighter sibling for high-volume routing or step up to Meta's flagship reasoning tier:
Llama 4 Behemoth
Llama 5
Muse Spark 1.1
Llama 4 Maverick
Llama 4 Scout
Llama 3.3 70B
AI Glossary & Architecture Concepts
View full glossary →Key machine learning concepts and benchmarks relevant to Llama 3.2 90B Vision:
La unidad básica de texto que procesa un modelo de lenguaje, que normalmente equivale a 3 o 4 caracteres o aproximadamente 0,75 palabras. Por ejemplo, una frase típica se divide en varios tokens.
Un conjunto estandarizado de pruebas para evaluar y comparar objetivamente las capacidades de distintos modelos de IA en tareas como programación (SWE-bench) o matemáticas avanzadas (AIME).
La cantidad máxima de tokens que un modelo puede considerar a la vez, incluyendo tanto la entrada que lee como la salida que genera. Una ventana de 1.000.000 de tokens puede procesar unas 750.000 palabras en una sola petición.
La capacidad de un modelo de detectar la necesidad de una función externa y emitir argumentos JSON estructurados para ejecutar API, búsquedas web o consultas a bases de datos.
Un protocolo abierto desarrollado por Anthropic que permite a los agentes de IA conectarse de forma estandarizada a sistemas de archivos locales, entornos de desarrollo y servicios externos.
Una red neuronal multimodal diseñada para interpretar, razonar y generar contenido combinando simultáneamente imágenes, diagramas, capturas de pantalla y texto en lenguaje natural.
Las puntuaciones de benchmarks, precios por token y límites de tasa evolucionan rápidamente. Verifique siempre las especificaciones actuales en la documentación oficial del proveedor.
Fuentes: Meta AI Llama 3.2 Official Release↗